© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 949
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or brands in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    124
    +0.05
    0.1%
    959
    +0.05
    0.1%
    1386
    +0.05
    0.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.05
    0.02
    1343
    +0.05
    0.04
    1120
    +0.05
    0.02
    Negative Logits
    vitis
    -0.58
    ochond
    -0.55
     aload
    -0.54
    ]<<"
    -0.53
     AssemblyCulture
    -0.53
    mkdirs
    -0.52
    gebob
    -0.52
     PyTuple
    -0.51
    logenetic
    -0.51
    RTEE
    -0.51
    POSITIVE LOGITS
     fto
    1.33
     alre
    1.29
     accla
    1.26
     guarante
    1.25
     inev
    1.25
     fep
    1.24
     ftu
    1.23
     increa
    1.23
     desir
    1.23
     encomp
    1.23
    Activations Density 0.040%

    No Known Activations